# ！/usr/bin/python3
# -*- coding: utf-8 -*-
# 在项目根目录下新建：run.py
from scrapy.cmdline import execute
# 第三个参数是：爬虫程序名
# --nolog什么意思？
execute([\'scrapy\', \'crawl\', \'lianjiaBj\', \'--nolog\'])

import scrapy
# -*- coding: utf-8 -*-
from lianjia.items import LianjiaItem
from selenium.webdriver import ChromeOptions
from selenium.webdriver import Chrome
import json

# 引入文件1max_beijing.json，利用文件内的url网址信息
with open(\'1max_beijing.json\', \'r\') as file:
    str = file.read()
    data = json.loads(str)


class LianjiabjSpider(scrapy.Spider):
    name = \'lianjiaBj\'
    # allowed_domains = [\'bj.lianjia.com\']

    start_urls = data

    # 实例化一个浏览器对象
    def __init__(self):
        # 防止网站识别Selenium代码
        # selenium启动配置参数接收是ChromeOptions类，创建方式如下：
        options = ChromeOptions()
        # 添加启动参数
        # 浏览器不提供可视化页面. linux下如果系统不支持可视化不加这条会启动失败
        options.add_argument("--headless")  # => 为Chrome配置无头模式
        # 添加实验性质的设置参数
        # 设置开发者模式启动，该模式下webdriver属性为正常值
        options.add_experimental_option(\'excludeSwitches\', [\'enable-automation\'])
        options.add_experimental_option(\'useAutomationExtension\', False)
        # 禁用浏览器弹窗
        self.browser = Chrome(options=options)
        # 最新解决navigator.webdriver=true的方法
        self.browser.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {
            "source": """
                                   Object.defineProperty(navigator, \'webdriver\', {
                                     get: () => undefined
                                   })
                                 """
        })

        super().__init__()

    def start_requests(self):
        print("开始爬虫")
        url = self.start_urls
        print("开始接触url")
        print(type(url))
        count = 0
        # 逐个引入1max_beijing.json文件中url信息
        for i in url:
            count += 1
            alone_url = i[\'BeiJingFangYuan_Id\']  # dataNum为 str类型的地址
            # print(alone_url)

            # print("url", url)
            # 访问下一页，有返回时，调用self.parse_details方法
            response = scrapy.Request(url=alone_url, callback=self.parse_details)
            yield response
        print("本次爬取数据: %s条" % count)

        # 一个Request对象表示一个HTTP请求，它通常是在爬虫生成，并由下载执行，从而生成Response
        # url（string） - 此请求的网址
        # callback（callable） - 将使用此请求的响应（一旦下载）作为其第一个参数调用的函数。
        # 如果请求没有指定回调，parse()将使用spider的 方法。请注意，如果在处理期间引发异常，则会调用errback。
        # 仍有许多参数：method=\'GET\', headers, body, cookies, meta, encoding=\'utf-8\', priority=0, dont_filter=False, errback
        # response = scrapy.Request(url=url, callback=self.parse_index)      #
        # yield response

        # 整个爬虫结束后关闭浏览器
        def close(self, spider):
            print("关闭爬虫")
            self.browser.quit()

    \'\'\' # 访问主页的url, 拿到对应板块的response
    def parse_index(self, response):
        print("访问主页")

        for i in range(0, 2970):
            # 下一页url
            url = url[i][\'BeiJingFangYuan_Id\']
            i += 1
            print("url", url)
            # 访问下一页，有返回时，调用self.parse_details方法
            yield scrapy.Request(url=url, callback=self.parse_details)\'\'\'

    def parse_details(self, response):
        # 获取页面中要抓取的信息在网页中位置节点
        node_list = response.xpath(\'//div[@class="introContent"]\')

        try:
            # 基本属性
            # 房屋户型
            fangWuHuXing = node_list.xpath(\'./div[@class="base"]//li[1]/text()\').extract()
            if not fangWuHuXing:
                fangWuHuXing = "房屋户型为空"
            print("fangWuHuXing", fangWuHuXing)

            # 交易属性
            # 挂牌时间
            guaPaiShiJian = node_list.xpath(\'./div[@class="transaction"]//li[1]/span[2]/text()\').extract()
            if not guaPaiShiJian:
                guaPaiShiJian = "挂牌时间为空"
            print("guaPaiShiJian", guaPaiShiJian)


            # item
            item = LianjiaItem()
            item[\'fangWuHuXing\'] = fangWuHuXing
            item[\'guaPaiShiJian\'] = guaPaiShiJian
            yield item
        except Exception as e:
            print(e)

# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html

import scrapy


class LianjiaItem(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    # 基本属性
    # 房屋户型
    fangWuHuXing = scrapy.Field()


    # 交易属性
    # 挂牌时间
    guaPaiShiJian = scrapy.Field()
    # pass

# Define your item pipelines here
#
# Don\'t forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html


# useful for handling different item types with a single interface
from itemadapter import ItemAdapter
import codecs,json
class LianjiaPipeline(object):
    def __init__(self):
        # python3保存文件 必须需要\'wb\' 保存为json格式
        # self.f = open("1max_BJ_information.json", \'wb\')
        self.file = codecs.open(\'1max_BJ_information.json\', \'w\', encoding="utf-8")


    def process_item(self, item, spider):
        # 读取item中的数据 并换行处理
        content = json.dumps(dict(item), ensure_ascii=False) + \',\n\'
        self.file.write(content)

        return item

    def close_spider(self, spider):
        # 关闭文件
        self.file.close()

# Scrapy settings for lianjia project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://docs.scrapy.org/en/latest/topics/settings.html
#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = \'lianjia\'

SPIDER_MODULES = [\'lianjia.spiders\']
NEWSPIDER_MODULE = \'lianjia.spiders\'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = \'lianjia (+http://www.yourdomain.com)\'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# Configure maximum concurrent requests performed by Scrapy (default: 16)
#CONCURRENT_REQUESTS = 32

# Configure a delay for requests for the same website (default: 0)
# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
#DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)
#COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False

# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
#   \'Accept\': \'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8\',
#   \'Accept-Language\': \'en\',
#}

# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    \'lianjia.middlewares.LianjiaSpiderMiddleware\': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    \'lianjia.middlewares.LianjiaDownloaderMiddleware\': 543,
#}

# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    \'scrapy.extensions.telnet.TelnetConsole\': None,
#}

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
    \'lianjia.pipelines.LianjiaPipeline\': 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = \'httpcache\'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = \'scrapy.extensions.httpcache.FilesystemCacheStorage\'